Underwater Acoustic Source Localization via Kernel Extreme Learning Machine

Fiber-optic hydrophones have received extensive research interests due to its advantage in ocean underwater target detection. Here, kernel extreme learning machine (K-ELM) is introduced to source localization in underwater ocean waveguide. As a data driven machine learning method, K-ELM do not need priori environment information compared to conventional method of match field processing. The acoustic source localization is considered as a supervised classification problem, and the normalized sample covariance matrix (SCM) formed over a number of snapshots is utilized as input. The K-ELM is trained to classify SCMs into different depth and range classes with simulation. The source position can be estimated directly from the normalized SCMs with K-ELM. The results show that K-ELM method achieves satisfactory high accuracy both on range and depth localization. The proposed K-ELM method provides an alternative approach for ocean underwater source localization, especially in the case with less priori environment information.